相关论文: Multi-granularity Interactive Attention Framework …

Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not…

Bimanual manipulation presents unique challenges compared to unimanual tasks due to the complexity of coordinating two robotic arms. In this paper, we introduce InterACT: Inter-dependency aware Action Chunking with Hierarchical Attention…

This paper presents a novel hierarchical alignment model (HAM) that learns multi-granularity visual and linguistic representations in an end-to-end manner. We extract key points and proposal points to model 3D contexts and instances, and…

All-in-One Image Restoration (AiOIR) has advanced significantly, offering promising solutions for complex real-world degradations. However, most existing approaches rely heavily on degradation-specific representations, often resulting in…

Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly revealed appearance, occlusion, and motion blurs. In this…

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a…

Human-Object Interaction (HOI) detection aims to simultaneously localize human-object pairs and recognize their interactions. While recent two-stage approaches have made significant progress, they still face challenges due to incomplete…

Enabling bi-directional retrieval of images and texts is important for understanding the correspondence between vision and language. Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner.…

For extracting a target speaker voice, direction-of-arrival (DOA) estimation is crucial for binaural hearing aids operating in noisy, multi-speaker environments. Among the solutions developed for this task, a deep learning convolutional…

Speech-related Brain Computer Interface (BCI) technologies provide effective vocal communication strategies for controlling devices through speech commands interpreted from brain signals. In order to infer imagined speech from active…

Instruction tuning is widely used to improve a pre-trained Multimodal Large Language Model (MLLM) by training it on curated task-specific datasets, enabling better comprehension of human instructions. However, it is infeasible to collect…

Hearing-impaired individuals often face significant barriers in daily communication due to the inherent challenges of producing clear speech. To address this, we introduce the Omni-Model paradigm into assistive technology and present…

Audio-visual speech enhancement system is regarded as one of promising solutions for isolating and enhancing speech of desired speaker. Typical methods focus on predicting clean speech spectrum via a naive convolution neural network based…

We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a…

This review is focused on the data-driven approaches applied in different applications of Acoustic-to-Articulatory Inversion (AAI) of speech. This review paper considered the relevant works published in the last ten years (2011-2021). The…

This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a…

Pronunciation assessment models designed for open response scenarios enable users to practice language skills in a manner similar to real-life communication. However, previous open-response pronunciation assessment models have predominantly…

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Precision pathology relies on detecting fine-grained morphological abnormalities within specific Regions of Interest (ROIs), as these local, texture-rich cues - rather than global slide contexts - drive expert diagnostic reasoning. While…

Existing attention mechanisms are trained to attend to individual items in a collection (the memory) with a predefined, fixed granularity, e.g., a word token or an image grid. We propose area attention: a way to attend to areas in the…